Person Re-identification (ReID) aims to match people across non-overlapping camera views in a public space, which is usually regarded as an image retrieval problem to match query images with pedestrian images in the gallery. It is challenging since many difficulties exist such as pose misalignments, occlusions, similar appearance when detecting people. Existing researches on ReID mainly focus on two major problems: representation learning and metric learning. In this paper, we target at learning discriminative representations and make two contributions in total. ( $i$ ) We propose a novel architecture named Deeply Associative Two-stage Representations Learning (DATRL). It contains the global re-initialization stage and fully-perceptual classification stage employing two identical CNNs associatively at the same time. On the global stage, we take on the backbone of one deep CNN e.g., dozens of layers in the front of Resnet-50 as a normal re-initialization subnetwork. Meanwhile, we apply our own proposed 3D-transpose technique into the backbone of the other CNN to form the 3D-transpose re-initialization subnetwork. The fully-perceptual stage is actually made up of the leftover layers of the original CNNs. On this stage, we take both the global representations learned at multiple hierarchies and the local representations uniformly-partitioned on the highest conv-layer into consideration, and then optimizing them separately for classification. ( $ii$ ) We introduce a new joint loss function in which our proposed Labels Interval Extension loss (LIEL) and Group loss (GL) are combined to enhance the performance of gradient decent as well as increasing the distances between image features with different identities. We apply the above DATRL, LIEL and GL to ReID thus obtaining DATRL-ReID. Experimental results on four datasets CUHK03, Market-1501, DukeMTMC-reID and MSMT17-V2 demonstrate that DATRL-ReID shows excellent performance in improving recognition accuracy and is superior to state-of-the-art methods.

中文翻译：

---

基于标签间隔扩展损失和群体损失的深度关联两阶段表示学习，用于人员重新识别

行人重识别 (ReID) 旨在在公共空间中通过非重叠的摄像机视图匹配人，这通常被认为是将查询图像与图库中的行人图像进行匹配的图像检索问题。它具有挑战性，因为在检测人时存在许多困难，例如姿势错位、遮挡、相似的外观。现有关于 ReID 的研究主要集中在两个主要问题：表示学习和度量学习。在本文中，我们的目标是学习判别式表示，总共做出了两个贡献。( $i$ ) 我们提出了一种名为深度关联两阶段表示学习 (DATRL) 的新颖架构。它包含同时关联使用两个相同 CNN 的全局重新初始化阶段和完全感知分类阶段。在全球舞台上，我们采用一个深度 CNN 的主干，例如，Resnet-50 前面的几十层作为正常的重新初始化子网络。同时，我们将我们自己提出的 3D-transpose 技术应用到另一个 CNN 的主干中，以形成 3D-transpose 重新初始化子网络。完全感知阶段实际上由原始 CNN 的剩余层组成。在这个阶段，我们同时考虑在多个层次上学习的全局表示和在最高卷积层上均匀划分的局部表示，然后分别优化它们以进行分类。( $ii$ ) 我们引入了一个新的联合损失函数，其中我们提出的标签间隔扩展损失（LIEL）和组损失（GL）相结合，以提高梯度下降的性能，并增加具有不同身份的图像特征之间的距离. 我们将上述 DATRL、LIEL 和 GL 应用于 ReID，从而获得 DATRL-ReID。在 CUHK03、Market-1501、DukeMTMC-reID 和 MSMT17-V2 四个数据集上的实验结果表明，DATRL-ReID 在提高识别精度方面表现出优异的性能，并且优于最先进的方法。